AGENT SKILL

joss-audit

Evaluate an R or Python package and its paper.md against the full JOSS reviewer checklist. Launches the joss-reviewer agent (software, community, and field specialists in parallel) and returns a gap report with Critical, Major, and Minor findings, then offers fixes.

License 许可
MIT
最近更新
2026-10-23
Stars
★ 0
Forks
0

01 前言 Front Matter

name
joss-audit
description
Evaluate an R or Python package and its paper.md against the full JOSS reviewer checklist. Launches the joss-reviewer agent (software, community, and field specialists in parallel) and returns a gap report with Critical, Major, and Minor findings, then offers fixes.
argument-hint
[package path]

03 SKILL.md 正文

JOSS Submission Audit

Thin launcher: the audit workflow lives in the pub-pipeline:joss-reviewer agent. This skill gathers context, dispatches it, answers its questions in the main session (subagents cannot ask the user), and offers fixes.

1. Gather context (Read tool)

  • Package root: $ARGUMENTS if given, else the current directory (must contain DESCRIPTION or pyproject.toml).
  • Read .claude/pub-pipeline.local.md if it exists. If missing, offer to create it from ${CLAUDE_PLUGIN_ROOT}/docs/user-config-template.md.

2. Dispatch (Agent tool)

Launch subagent_type: pub-pipeline:joss-reviewer with:

<context>
<package_root>[absolute path]</package_root>
<user_config>[frontmatter of .claude/pub-pipeline.local.md, or "none"]</user_config>
</context>

3. Present and resolve

Present the report. If it ends with a Decisions Needed block, ask the user each question; when an answer changes a checklist result (e.g. confirming the submitting author is a major contributor), update that item yourself. Re-dispatch only if an answer requires new evidence to be gathered.

4. Offer to fix

Offer the automatable fixes the report calls for:

  • No paper.md or weak sections: /pub-pipeline:joss-draft
  • Add CONTRIBUTING.md (bug reports, PRs, support)
  • Add missing ORCID fields, fix frontmatter (%e %B %Y date), add the AI usage disclosure section
  • Add missing BibTeX entries sourced from DOIs

Re-run this audit after fixes.

04 同仓库更多 Skills

Abdulqudduz
Abdulqudduz/claude-anvil

worldsmith-methodology

Use when working in a project with a worldbuilding documentation ecosystem (docs/ or lore/ directory). Provides the documentation-first methodology: canonical hierarchy, doc roles (timeline, lore, characters, systems), propagation discipline, and the dual canonical and exploratory workflow.

★ 0
Abdulqudduz
Abdulqudduz/claude-anvil

prose-craft

Use when writing fiction, editing fiction prose, reviewing chapters, or drafting scenes. Covers prose craft, dialogue mechanics, scene structure, and common failure modes in AI-assisted fiction. Trigger phrases: "write fiction", "edit chapter", "prose review", "scene draft", "dialogue check", "fiction craft", "edit this scene", "review my prose".

★ 0
Abdulqudduz
Abdulqudduz/claude-anvil

vista

This skill should be used when the user asks about research directions, open problems, future work, or follow-up research from the academic literature. Trigger phrases include "open problems in X", "what's next for Y", "future work for paper Z", "research directions on T", "salient follow-up research", "what should I work on next in", "find me follow-up research unrelated to my prior work", "broad survey of W", "neglected directions in V". Routes the request to the right Vista MCP tool, reads back the structured paper sections, and synthesizes research directions in the conversation.

★ 0
Abdulqudduz
Abdulqudduz/claude-anvil

synthesize

Make a research-agent run conclude and write synthesis.md (outcome, key findings, failed approaches, open questions, recommendations). Signals a live researcher to wrap up, or launches one in synthesis mode when none is running. Use when results are good enough or the agent is stalling.

★ 0
Abdulqudduz
Abdulqudduz/claude-anvil

status

Show the current state of a research-agent run from .research/: liveness, cycles and budget, sub-problem and hypothesis statuses, eval trend, current focus, and branches. Read-only.

★ 0
Abdulqudduz
Abdulqudduz/claude-anvil

resume

Resume an interrupted research-agent run from .research/. Re-launches the researcher to reload its structured state and continue from the current focus, optionally on a named branch or with a new budget. Use after a session restart, crash, or explicit pause.

★ 0